UNITED STATES PATENT AND TRADEMARK OFFICE
`
`
`
`
`
`
`BEFORE THE PATENT TRIAL AND APPEAL BOARD
`
`
`
`
`
`
`
`
`GOOGLE LLC,
`
`Petitioner,
`
`v.
`
`JAWBONE INNOVATIONS, LLC,
`
`Patent Owner.
`
`
`
`
`
`
`
`
`Case IPR2022-01027
`
`Patent No. 8,467,543
`
`
`
`
`
`
`
`
`Declaration of Shauna L. Wiest Regarding Hussain
`
`
`
`
`
`
`
`
`Page 1 of 38
`
`GOOGLE EXHIBIT 1010
`
`

`

`
`
`I.
`
`Declaration of Shauna L. Wiest
`
`
`I, Shauna L. Wiest, state and declare as follows:
`Introduction
`I have prepared this Declaration in connection with the Petition for
`1.
`
`Inter Partes Review of U.S. Patent No. 8,467,543, which I understand will be
`
`filed concurrently with this Declaration.
`
`2.
`
`I am currently a senior research analyst with the Research &
`
`Information Services team at Finnegan, Henderson, Farabow, Garrett &
`
`Dunner, LLP, located at 901 New York Avenue, NW, Washington, DC 20001-
`
`4413.
`
`3.
`
`I am over eighteen years of age, and I am competent to make this
`
`Declaration. I make this Declaration based on my own personal knowledge,
`
`and my knowledge of library science practices.
`
`4.
`
`I earned a Master of Science in Library Science from the
`
`University of North Carolina at Chapel Hill in 1999, and a Bachelor of Arts in
`
`Political Science from the University of California at San Diego in 1989. I
`
`have worked as a law librarian for over twenty years. I have been employed in
`
`the Research & Information Services Department at Finnegan, Henderson,
`
`Farabow, Garrett & Dunner, LLP since 2021. Before that, from 2000-2015, I
`
`was employed as a Law Librarian at Stoel Rives LLP, and from 2015-2016, I
`
`was employed as a Competitive Intelligence Specialist for Nossaman LLP.
`
`
`
`2
`
`Page 2 of 38
`
`

`

`
`II.
`
`Declaration of Shauna L. Wiest
`
`
`Standard Library Practice for Receiving, Cataloging, and Making
`Materials Publicly Available
`I have knowledge of and experience with standard library practices
`5.
`
`regarding the receipt, cataloging, and making materials available to the public. I
`
`have knowledge of and experience with the Machine-Readable Cataloging
`
`(MARC) system, an industry-wide standard that libraries use to catalog
`
`materials. I also have knowledge of and experience with OCLC (previously
`
`called Online Computer Library Center, Inc.) and OCLC Control Numbers,
`
`which are unique accession numbers assigned by the OCLC system when a
`
`bibliographic record is cataloged and made available to the public through
`
`WorldCat. OCLC control numbers are often used by the public to search for
`
`specific records within WorldCat, the latter being an online database of
`
`520,593,877 bibliographic records from approximately 72,000 libraries as of
`
`December
`
`2021
`
`(Source:
`
`https://www.oclc.org/en/worldcat/inside-
`
`worldcat.html).
`
`6.
`
`By the mid-1970s, standard library practice involved cataloging
`
`items utilizing the MARC system. The MARC system was developed during the
`
`1960s to standardize bibliographic records so they could be read by computers and
`
`shared among libraries. By the mid-1970s, MARC had become the international
`
`standard for bibliographic cataloging and is still used today.
`
`
`
`3
`
`Page 3 of 38
`
`

`

`
`
`7.
`
`Many libraries provide public access to their MARC records via the
`
`Declaration of Shauna L. Wiest
`
`
`Internet and/or their public catalog systems at the library. The MARC record
`
`system uses a specific three-digit numeric code (from 001-999) to identify each
`
`field in a catalog record. For example, field tag 008 provides the six-digit date the
`
`item was cataloged (Date entered on file). The first six characters of field tag 008
`
`are always in the “YYMMDD” format. Field tag 245 identifies the full title
`
`statement of the work; field tags 260 and 264 denotes the place of publication,
`
`including date of publication, distribution, and copyright for the item; and field tag
`
`300 identifies the physical description, often including holdings information, for
`
`the work.
`
`8.
`
`Based on standard library practice, when a library receives an item,
`
`it stamps the item with the library name and often with a date that is within a few
`
`days or weeks of receipt. Next, the library will catalog the item within a matter of a
`
`few days or weeks of receiving it.
`
`9.
`
`Generally, after an item is cataloged, the public may access the item
`
`by searching a catalog, browsing the shelves, and either requesting or
`
`electronically accessing the item from the library. Standard library practice is to
`
`make the item available to the public within a few days or weeks of cataloging it.
`
`III. MARC Records for Hussain
`This Declaration relates to the dates of receipt and public
`10.
`
`availability of the following: Amir Hussain, Douglas R. Campbell, and
`4
`
`
`
`Page 4 of 38
`
`

`

`
`Thomas J. Moir, A New Metric For Selecting Sub-Band Processing in Adaptive
`
`Declaration of Shauna L. Wiest
`
`
`Speech Enhancement Systems, presented at Eurospeech ’97: 5th European
`
`Conference on Speech Communication and Technology, Rhodes, Greece, 22-
`
`25 September 1997 (“Hussain”). The Hussain reference appears at page 2611,
`
`identified by paper number ThAA.15, in Volume V of the Eurospeech ’97
`
`Conference Proceedings. I understand that Hussain has been submitted as
`
`Exhibit 1006 in this proceeding.
`
`11.
`
`Appendix A to this declaration is a true and correct copy of Hussain
`
`obtained from The Ohio State University Library. Appendix A includes the front
`
`matter and table of contents for Volume V containing Hussain. Appendix A also
`
`contains handwritten notes identifying the call number for Hussain as P95 E88
`
`1997 V. 5.
`
`12.
`
`Appendix B to this declaration is a true and accurate copy of the
`
`MARC catalog record from The Ohio State University for its copy of Eurospeech
`
`’97 containing Hussain, downloaded from https://library.ohio-
`
`state.edu/search~S7?/.b5440967/.b5440967/1%2C1%2C1%2CB/marc~b5440967
`
`on May 17, 2022.
`
`13.
`
`In The Ohio State University MARC catalog record, the fixed data
`
`elements of MARC field 008 are listed as 000630s1997. This indicates that
`
`Eurospeech ’97 containing Hussain was cataloged by The Ohio State University on
`
`June 30, 2000. The subfield “code “s” appearing in MARC field 008 refers to the
`5
`
`
`Page 5 of 38
`
`

`

`
`“single known date” for the item, which in this catalog record is 1997. Based on
`
`Declaration of Shauna L. Wiest
`
`
`standard library practices, Hussain would have been shelved and made available to
`
`the public a few days or weeks after June 30, 2000.
`
`14.
`
`In The Ohio State University MARC catalog record, the Title
`
`Statement field 245 denotes the title and statement of responsibility for the work as
`
`Eurospeech 97 :|b5th European Conference on Speech Communication and
`
`Technology : Rhodes, Greece, 22-25 September, 1997. The subfield code “b”
`
`refers to the remainder of the title, which in this record is 5th European Conference
`
`on Speech Communication and Technology : Rhodes, Greece, 22-25 September,
`
`1997.
`
`15.
`
`Field 264 of The Ohio State University MARC catalog record
`
`denotes the place of publication, distribution, and date/copyright information for
`
`Eurospeech ’97 containing Hussain. Field 264 is identified as Grenoble, France
`
`:|bESCA,|c[1997]. The subfield code “b” refers to the name of the producer,
`
`publisher, distributor, or manufacturer, which in this record is ESCA, or European
`
`Speech Communication Association. The subfield code “c” refers to the copyright
`
`date, which for this record is 1997.
`
`16.
`
`Field 300 of The Ohio State University MARC catalog record
`
`identifies the physical description and holdings of the item. The MARC catalog
`
`record denotes the physical description of Eurospeech ’97 containing Hussain as
`
`containing 5 volumes.
`
`
`6
`
`Page 6 of 38
`
`

`

`
`
`17.
`
`Appendix C to this declaration is a true and correct copy of The
`
`Declaration of Shauna L. Wiest
`
`
`Rutgers University Libraries MARC record for its copy of Hussain, which was
`
`downloaded from https://bit.ly/3sdtXkt on May 17, 2022
`
`18.
`
`In The Rutgers University Libraries MARC catalog record, the fixed
`
`data elements of MARC field 008 are listed as 990730s1997. This indicates that
`
`Eurospeech ’97 was cataloged by The Rutgers University Libraries on July 30,
`
`1999. The subfield “code “s” appearing in MARC field 008 refers to the “single
`
`known date” for the item, which for this catalog record is 1997. Based on standard
`
`library practices, Eurospeech ’97 would have been shelved and made available to
`
`the public a few days or weeks after July 30,1999.
`
`19.
`
`The Rutgers University Libraries MARC catalog record field tag 245
`
`denotes the title and statement of responsibility for the work as “Eurospeech '97 :
`
`$b5th European Conference on Speech Communication and Technology : Rhodes,
`
`Greece, 24-25 September 1997.”
`
`20.
`
`The Rutgers University Libraries MARC catalog record field tag 260
`
`denotes that Eurospeech ’97 was published in Patras, Greece by the European
`
`Speech Communication Association in 1997.
`
`21.
`
`Field 300 of the Rutgers University Libraries MARC catalog record
`
`identifies the physical description and holdings of the item. The MARC catalog
`
`record denotes the physical description of Eurospeech ’97 as 2 volumes
`
`(containing volumes 1 and 2). Based on the public availability of volumes 1 and 2,
`7
`
`
`Page 7 of 38
`
`

`

`
`other volumes, including volume 5, would have been made publicly available if
`
`Declaration of Shauna L. Wiest
`
`
`requested within a few days or weeks after July 30,1999.
`
`IV. OCLC Records for Hussain
`A public search of WorldCat lists nine individual OCLC catalog
`22.
`
`entries for Eurospeech ’97: 5th European Conference on Speech Communication
`
`and Technology: Rhodes, Greece, 22-25 September 1997, as of January 31, 2022.
`
`Appendix D to this declaration is a true and accurate copy of the list of the nine
`
`individual OCLC catalog entries from WorldCat containing Eurospeech ’97.
`
`Appendix D was downloaded from:
`
`https://www.worldcat.org/search?q=au%3Aeurospeech&dblist=638&fq=yr%3A19
`
`97&qt=facet_yr%3A on May 17, 2022. Each of the nine catalog entries can be
`
`accessed to view the libraries who have cataloged and made publicly available,
`
`Eurospeech ’97 containing Hussain.
`
`23.
`
`Appendix E to this declaration is a true and accurate copy of OCLC
`
`Control Number 105130238, which is among the nine individual OCLC catalog
`
`entries listed in Appendix D. Appendix E was downloaded from:
`
`http://www.worldcat.org/oclc/1051302387 on May 17, 2022 and lists the cataloged
`
`publicly available library holdings for OCLC Control Number 1051302387. OCLC
`
`Control Number 1051302387 denotes the date (1997) of the publication, the
`
`physical description (5 volumes), and title (EuroSpeech '97 : 5th European
`
`Conference on Speech Communication and Technology : Rhodes, Greece, 22-25
`8
`
`
`
`Page 8 of 38
`
`

`

`
`September, 1997 : proceedings) for the publication. Each of the eight other entries
`
`Declaration of Shauna L. Wiest
`
`
`in Appendix D list similar cataloging dates, physical description, title information,
`
`and publicly available library holdings information for Hussain.
`
`V. Conclusion
`In signing this Declaration, I understand it will be filed as
`24.
`
`evidence in a contested case before the Patent Trial and Appeal Board of the
`
`United States Patent and Trademark Office. I understand I may be subject to
`
`cross-examination in this case and that cross-examination will take place
`
`within the United States. If cross-examination is required of me, I will appear
`
`for cross-examination within the United States during the time allotted for
`
`cross-examination.
`
`25.
`
`I declare that all statements made herein of my knowledge are true,
`
`that all statements made on information and belief are believed to be true, and that
`
`these statements were made with the knowledge that willful false statements and
`
`the like so made are punishable by fine or imprisonment, or both, under Section
`
`1001 of Title 18 of the United States Code.
`
`
`
`Executed on May 17, 2022, in Washington, DC.
`
`
`
`
`
`
`
`
`
`Shauna L. Wiest
`
`9
`
`Page 9 of 38
`
`

`

`
`
`
`
`
`
`
`
`
`
`
`
`
`APPENDIX A
`APPENDIX A
`
`
`
`Page 10 of 38
`
`Page 10 of 38
`
`

`

`EUROPEAN SPEECH COMMUNICATION ASSOCIATION (ESCA)
`
`
`
`5th EUROPEAN CONFERENCE ON SPEECH ComMUNICATION AND TECHNOLOGY
`
`RHODES - GREECE
`
`22-25 September 1997
`
`UNDER THE AUSPICES OF
`
`THE MINISTRY OF CULTURE
`
`THE MINISTRY OF THE AEGEAN
`
`THE GENERAL SECRETARIAT OF SCIENCE AND RESEARCH
`
`PROCEEDINGS
`VOLUME 5
`
`
`
`092 ORGANIZER:
`ay UNIVERSITY OF PATRAS
`EX)
`— WIRE COMMUNICATIONS LABORATORY
`$
`261 10 Rion - Patras - Greece
`
`Page 11 of 38
`
`Page 11 of 38
`
`

`

`.
`Eurospeech °97
`6"Eurbpean Conference oxSpeech-Communication,qnd Technology ~
`
`
`EUROPEAN SPEECH COMMUNICATION ASSOCIATION (ESCA)
`
`5™ European Conference on Speech Communication and Technology:
`EUROSPEECH ’97
`
`Eurospeech 97 Proceedings
`ESCA 5" European Conference on Speech Communication and Technology
`I, 0, WI, IV, V
`G. Kokkinakis, N. Fakotakis, E. Dermatas
`1018-4074
`
`PIF
`ERS
`WT
`
`6
`
`:
`
`¥ "
`
`‘
`
`|
`}
`
`RRxe:
`
`Title:
`Subtitle:
`Volumes:
`Editors:
`ISSN:
`
`;
`
`fj
`~ FY
`wenF
`
`an
`
`‘
`
`5
`
`:
`
`4
`
`S4 on
`“
`
`pete yg
`?
`4
`TAA heat
`
`ef
`
`moe
`
`“
`
`?
`
`: %
`
`.
`
`Additional copies may be’ordered:from:
`
`ESCA- European Speech Communication Association
`ICP, Universite Stendhal,
`BP 25X, 38040 GRENOBLECedex 9, FRANCE
`
`.
`
`.
`
`-
`fe
`3°
`* i
`et = at
`
`Tel: (+33).4.76.82.43.36
`Fax: (4+33).4.76.82.43.35
`
`“
`
`" F
`;
`
`‘
`
`i
`i
`
`.
`
`Ai, *
`
`avs
`
`+
`
`-
`
`Teg,
`i
`
`4
`——
`.
`.
`5 \/
`Cover Design: Artemis Kokkinaki-Papapetrou
`Ne
`*
`WCL, University of Patras, Greece
`Edited at:
`Printed by:
`TYPOFFSET, K. Manonri-Stanidi, Patras, Greece
`
`.
`
`f
`
`ii
`
`Page 12 of 38
`
`~
`
`=
`
`_
`
`Page 12 of 38
`
`

`

`“Eurospeech °97
`5“ European Conference on Speech Communication and Technology
`
`.
`
`VOLUME 5
`
`a
`
`
`
`ThMD.1 Gaussian Mixture Models withCommon Principal
`Axes and Their Application in Text-Indépendént Speaker
`Tdlemtification.............-cccccssecsesessssesseescserssesosacerensessaeaens 2279
`Kuo-Hwei Yuo, Hsiao-Chuan Wang
`National Tsing Hua Univ., ROChina
`
`‘
`
`‘
`
`ThMD.2 Speaker Models Designed from Complete Data
`Sets: ‘A New Approach to Text-Independent Speaker
`Verification 0.0... csceeessnsscsstsesessacsesnressessssenseenseaneeene 2283
`Dominik R. Dersch, *Robin W. King
`Univ. ofSydney, Australia
`*Univ. ofSouth Australia, Australia.
`
`‘
`
`ThMD.3 A Double Gaussian Mixture Modeling Approach
`To Speaker Recognition ............05ceitscsessesaesseesesoeeees 2287
`Vergin Rivarol, Douglas O'Shaughnessy +
`-
`.
`INRS Telecommunications, Canada
`
`ThMD.12 Foreign Speaker Accent Classification Using
`Phoneme-Dependent Accent Discrimination Models and
`Comparisons, with Human Perception Benchmarks
`Karsten Kumpf, *Robin W. King
`Univ. ofSydney, Australia
`*Untv. ofSouth Australia, AUStralic ....cseesssceeieeenen 2323
`
`ThMD.13 A Comparison of Human and MachineIn
`Speaker Recognition ................ccccsssssssessesseseensssenenengees ZIT
`Li Liu, Jialong He, Giinther Palm
`:
`Univ. of Ulm, Germany
`
`°
`
`ThMD.14 Evaluation of Second Language Learners’
`Pronunciation Using Hidden Markov Models............... 2331
`Simo M.A. Goddijn, *Guus de Krom
`Forensic Science Laborutory, Ridiswisk
`*Univ. ofUtrecht,The Netherlands
`
`i
`
`:
`
`ThMD.15 Delta Vector Taylor Series Environment
`Compensation for Speaker Recognition.................00+ 2335
`Brian Eberman, Pedro J. Moreno
`Digital Equipment Corp., USA
`
`.
`
`'
`ota
`
`Meay
`
`ThMD4A An Acoustic Subword Unit Approach to Non-
`Linguistic Speech Feature Identification..................-.-- 2291
`Mohamed Afify, Yifan Gong, Jean-Paul Haton
`CRIN-CNRS, France
`
`‘
`
`ThMD.16 Wavelet-Like Regression Features in the
`Cepstral Domain for Speaker Recognition. ...............00+ 2339
`Jonathan Hume
`°
`Univ. of Wales Swansea, UK
`
`ThMD.5 N-Best GMM’s for Speaker Identification..... 2295
`Chakib Tadj; *Pietre Dumouchel, {Yu Fang
`Ecole de Technologie Superieure, Canuda
`*Centre de Recherche Informatique, Canada
`finstitut Universituire de Technologie, Cundda
`
`,
`
`ThMD.17 Minimum Classitication Error Linear Regression
`(MCELR)for Speaker Adaptation Using HMM with Trend
`FRUINCHIONS 0. rsecesneseeeesnacseeneeabensseneeanseneeneasseeres 2343
`Rathinavelu Chengalvarayan
`Bell Labs-Lucent Technologies, USA
`
`.
`
`-
`
`THMD.6 Model Deperident Spectral Representations for
`Speaker Recognition.......scsesscsecssseessseeneenseneeseansssseseanees+2299
`Guillaume Gravier, *Chafic Mokbel, Gerard Chollet
`ENSTASIG, France
`*CNET-DIH/RCP, France
`
`.
`
`ThMD.18 A Continuous HMM Text Independent Speaker ~
`Recognition System Based on Vowel Spbiting............... 2347
`Nikos Fakotakis, *AnastasiosTsopanogion, Kallirroi Georgila
`
`Univ. ofPutras, Greece
`*KNOWLEDGESA, Greece
`
`; ThMD.7 Equalizing Sub-Band Exror-Rates in Speaker
`Recognitions ...........::ccscccccssseesseressesesnensassesssecsnansssesseresease 2303
`-Roland Auckenthaler, *John S. Mason
`*
`Technical Univ. Graz, Austria
`*Univ. of Wales Swansea, UK °
`
`,
`
`'
`
`ThMD.8 Automatic Gender Identification Under Adverse
`Conditions ......sssssssssssesscsesessccsesecescssesrsasnuntsnanesninevessesssnees 2307
`Stefan Slomka, Sridha Sridharan
`Queensland Univ. of Technology, Australia
`
`ThMD.9 Acoustic Features and Perceptive Processes in the
`Identification of Familiar Voices...2311
`Yizhar Lavner, Isak Gath, Judith Rosenhouse
`Israel Institute ofTechnology,Israel
`
`TEMD.10 Onthe Use Acoustic Segmentationiin|Speaker
`Tdemntification............ccccsssssesessssssscesssesssensesesescersceeasenenens 2315
`Leandro Rodriguez-Linares, Carmen Garcia-Mateo
`Univ. of Vigo, Spain
`ThMD.11 Speaker Recognition byHumans and Machines '
`Herman J.M. Steeneken, David A. Van Leeuwen
`:
`TNO-HERI, The Nethertainds wuicassrsesssccsressseesssnansre 2319
`
`ThMD.19 On the Independenceof Digits in Connected
`Digit Strrimgs...............ccccsssessctsessessssscssceseseasssereseneeseeneaes 2351
`Johan W. Koolwaaij, Lou Boves
`.
`wn
`{
`Nijmegen University, The Netherlands
`rls
`,
`ThMD.20 A New Procedure for Classifying Speakers in
`Speaker Verification Systems ..............2esanesennseeesdhereeseees 2355
`Johan W. Koolwaaij, Lou Boves
`+ Nijmegen University, The Netherlands
`q
`a
`.
`ThMD.21 Sound Channel Video Indexing............c008 2359
`Claude Montacie, Marie-Jose Caraty
`Univ. Pierre et Marie Curie - CNRS, France
`
`“
`
`ThMD.22 CDHMM Speaker Recognition By Means of
`Frequency Filtering of Filter-Bank Energies................ 2363
`Javier Hernando, Climent Nadeu
`Universitit Politecnicau de Catalunya, Spain
`
`-
`
`’
`
`'
`
`aat
`
`vy,
`
`4
`
`i
`
`
`Page 13 of 38
`
`Page 13 of 38
`
`

`

`Eurospeech:?97
`5” European Conference on Speech Communication and Technology
`
`Th3B.6 The Phonology and Phonetics of Second Language
`Intonation: The Case of "Japanese English”.................2411
`Motoko Ueyama
`UCLA, USA
`
`
`
`Th3C.1 Methods for Microphone Equalization in Speech
`Recogmition 0... eessssessssesssssssssssssssscssccsscenssesacaseacsoessseees 2415
`L. Fissore, Giorgio Micea, C. Vair
`
`CentroStudieLaboratori Telecomunicazioni(csEn)Italy *
`
`Th3C.2 Room Acoustics and Reverberation: Impact on
`Hands-Free Recognition .............0.ssssssssssssseseccsecneestesseess2419
`Satoshi Nakamura, Kiyohiro Shikano
`Nara Institute ofScience and Technology, Japan
`Th3C.3 Echo and Noise Reduction for Hands-Free
`Terminals -State of the Arte........cccccsscccssssssesssscssesegpetesees2423
`Gerard Faucon, Regine Le Rouquin-Jeannes
`Univ. de Rermes I, France
`
`Tbh3C4 Robust Speech Recognition forWireless Networks
`and Mobile Telephony.........c..csseess:Seasetescesnasnscaceseserseee2427
`Reinhold Haeb-Umbach
`Philips GmbH, Germany
`Th3C.5 Robust ASR for the Cellular EEnvironment.............
`Jay Naik
`Nynex, USA
`(Not arrived in time to be.included in the. Proceedings)
`
`Th3C.6 Speech Recognition in the Car From Phone Dialing
`to Car Navigation ..............sssssssscssesesssrsssssessasssnssssssseesnses2431
`Dirk Van Compernolle
`.
`Lernout & Hauspie Speech Products NV, Belgium
`
`1 T
`
`h3D.1 A Keyvowel Approachto the Synthesis of Regional
`Accents of English ...........cccsssssssssesssssssssssoresesesecsssessoessees2435
`+
`Briony Williams, Stephen Isard
`Univ. ofEdinburgh, UK
`
`-
`
`
`
`Th3A.1 Using Accent-Specific Pronunciation Modelling for
`Improved Large Vocabulary Continuous Speech
`Recognition...ccssesessssssssesssssssscsecscsesscnsesnenssesssseaessce 2367
`J. J. Humphries, P. C. Woodland
`Cambridge Univ., UK
`
`Th3A.2 Automatic Speech Recognition for Children
`Alexandros Potamianos, Shrikanth Narayana, Sungbok Lee
`AT&TLabs-Resectrch,, USA.ccccccccsscssssssssessecssasssssvsssecsescee2371
`Th3A.3 Recognition of Non-Native Accents.................. 2375
`Carlos Teixeira, Isabel Trancoso, Antonio Serralheiro
`INESC, Portugal
`
`Th3A.4 Speaking Mode Dependent Pronunciation
`Modeling in Large Vocabdlary Conversational Speech’
`Recognition .........ccc ec ccessssssssecessetesensssssssenssseactcsaseecesens 2379
`Michael Finke, Alex Waibel
`Curnegie Mellon Univ., USA
`
`Th3A.5 A Prosody-Only Decision-Tree Model for
`Disfluency Detection........ feteeessaccaseecsesssesnseceesssonsecoesassasace 2383
`Elizabeth Shriberg, "Rebecca Bates, Andreas Stolcke
`SRI International, USA
`*Boston Univ., USA
`
`'
`
`Th3A.6 A Novel Training Approachfor Improving Speech
`Recognition Under Adverse Stressful Conditions ......... 2387
`Sahar E. Bou-Ghazale, John H.L Hansen
`Duke Univ., USA
`
`
`
`Th3B.1 From PhoneIndentification to Phone Clustering
`Using Mutual Information............00..ssssessssssasssssssesscseses 2391
`Peter O’Boyle, Ji Ming, Marie Owens, F.Jack Smith
`Queen's Univ. ofBelfast, N. fretand
`
`4
`
`Th3B.2 Phonetic Code Emergencein a Society of Speech -
`Robots: Explaining Vowel Systems and the MUAF *
`Primeiplecs...cessesssssssessscssessssssesssssseessccatcssesasesussanesessaues 2395
`Ahmed-Reda Berrah, Rafael Laboissiere
`Institut de la Communication Purleé, France
`
`7
`
`4
`
`Th3B.3 Effects of Voicing on /t,d/ Tongue/Palate Contact in
`English and Norwegian..............ccccccscsssssssssssssscsescessseeseees 2399
`Inger Moen, Hanne Gram Simonsen
`Univ. ofOslo, Norway
`
`Th38.4 Fieldwork Techniques for Relating Formant
`Frequency;Amplitude and Bandwidth ....0..2..00.cccc.s. 2403
`Peter Ladefoged, *Gunnar Fant
`=.
`i
`UCLA, USA
`*KTH, Sweden
`
`Th3B.S Word Juncture Modelling Based on the TIMIT
`Database........ccccesssssecsccncsessesssesscsecsessssssssssessesaessesuseeascase 2407
`Xue Wang, Louis C.W. Pols
`Univ. ofAmsterdum, The Netherlands
`
`Th3D.2 Experimental Implementation of Pitch-
`Synchronous Synthesis Methods for the ROMVOX Text-té-
`Speech System...............cccssesssessssssesssssesecsenspent teseanessens2439
`Attila Ferencz, Radu Arsinte, *Istvan Nagy, Teodora Ratiu,
`Maria Ferencz, fGavril Toderean, +Diana Zaiu, Tunde-Cilla
`Kovacs, Lajos Simon
`Software ITC SA, Romania
`*Music Academy Gh.Dima, Romania
`fTechnical Univ. ofCluj-Napoca, Romani
`
`¢
`
`Th3D.3 The Bell Labs German Text-to-Speech System: An
`OVONVIOW 0...secs scessssescecesecsessasecsesssvessssastscctsssneestessussussneees2443
`Bernd Mobius, Richard Sproat,Jan P.A vanSanten, Joseph P.
`Olive
`Bell Labs-Lucent Technologies, USA
`
`xiii
`
`Page 14 of 38
`
`Page 14 of 38
`
`

`

`Eurospeech 97
`5" European Conference on Speech Communication and Technology
`ieee
`
`«
`
`Th4B.3 Perception of Noised Words by, Normal Children
`, and Children with Speech and Language Impairments
`Valentina V. Lyblinskaja, *Inna V. Koroldva, A.N.’Kornev,
`2 Blena V. Tagounova........ccssscesseseesagecssesecsessssnsscanseneesgereeee 2491
`PavlovInstitute ofPhysiology, Russia
`*Institute-ofEur, Throat, Nose und Speech Pathology, Russia
`
`Th4B.4 Modeling the Perception of Simultaneous’Semi-
`VOWelS...cccsssssscssesssssessecsscsecessevasscsecsassaneseccecsesaacevecssenenseeees 2495
`Georg F. Meyer, William.A Ainsworth
`Keele Univ., UK
`
`Th4B.5 Properties of Auditory Model Representations
`Fernando Santos Perdigao, Luis V. Sa
`Universidude de Coimbra, Portugal ..ccccscccssseresestsssess 2499
`
`Th4B.6 Impactof "Ascending Sequence" AI (Auditory
`Primary Cortex) Cells on Stop Consonant Perception"
`‘
`Marta Eduardo Sa, de*Sa Luis Vieira
`Universidade de Coimbret, Portugal ..cccccccssesesssclessoseceee 2503
`
`
`
`Th4C.1 Application-Dependent Prosodic Models for Text-
`To-Speech Synthesis and Automatic Design of Learning
`Database Corpus Using Genetic Algorithm. «................ 2507
`Olivier Boeffard,Emerard F.
`France Telecom-CNET, France
`
`Th4C.2 Combinatorial Issues in Text-To-Speech Synthesis
`Jan P.H. van Santen
`Bell Labs-Lucent Technologies, USA o.cssccsssssserepnesssscaseee 2511
`
`Th4C.3 Automatic Corpus-Based Training of Rules for
`Prosodic Generation in Text-To-Speech .....0.... cscs 2515
`Eduardo Lopez-Gonzalo, Jose M. Rodriguez-Garcia, Luis
`Hernandez-Gomez,Juan M.Villar
`ETSIT-UPM,Spain
`
`wk
`
`Th4C.4.Hidden Markov Model Based Voice Conversion
`Using Dynamic Characteristics of Speaker ................... 2519
`Eun-Kyoung Kim, Sangho Lee, Yung-Hwan Oh
`sl
`KAIST, Korea
`
`.
`
`Th4C.5 Speaker Interpolation in HMM-Based Speech
`Synthesis System ........sccsssessesssssssssesesssessatsessessesssssneess 2529
`Takayoshi Yoshimura, *Takashi Masuko, Keiichi Tokuda,
`:
`+
`*Takao Kobayashi,Tadashi Kitamura
`Nagoya Institute ofTechnology, Japun
`*Tokyo Institute ofTechnology, Jupun
`
`:
`
`‘
`
`“oe
`
`”
`
`Th3D.4 The Generation of Regional Pronunciations of
`English for Speech Synthesis ........... agevee Bove seasansasssuasasenses 2447
`Susan Fitt
`Univ. ofEdinburgh,UK
`
` «
`
`.
`
`tte
`
`Th3D.5 Bell Laboratories Russian Text-To-Speech System
`Elena Pavlova, -Yuri:Pavlov, Richard Sproat, Chilin Shih, Jan
`P.H.van Santen
`Bell Labs-Lucent Technologies, USA v.ssssssessserrseeecessrereeee 2451
`
`Th3D.6 A Bilingual Text-To‘Speech System iin Spanish and
`
`Catalan ..ccccceccccceccccccseeecesceseleeceaeacsece ceaeecelesseensssasessuseaaees 22455
`Antonio Bonafonte, Ignasi Esquerra, Albert Febrer, Francesc
`Vallverdu
`*
`Universitdt Politecnicu de Cutalunya, Spain .
`
`
`
`Th4A.1 Automatic Rule-based Generation of Word
`Pronunciation Networks .............sces cessesvieeessceusseareases 2459
`Nick Cremelie, Jean-Pierre Martens
`Univ. of Gent, Belgium
`
`Th4A.2 Creating User Defined New Vocabularies for Voice
`Dialing wo.cecscssccsssesssssssscesssnavassencsesscstoesseceeseeeectastseneassaneens 2463
`Jose Maria Elvira, Juan Carlos Torrecilla, Javier Caminero
`Telefonicu I+D, Spain
`
`Th4A.3 Automatic Generation of Context-Dependent
`Pronunciations ............sessesccessessseesesssesseeesseeseeeaeersess sasesses 2467
`Mosur Ravishankar, Maxine Eskenazi
`Carnegie Mellon Univ., USA
`
`Th4A.4 Automatic Generation of a Pronunciation
`Dictionary Based on a Pronunciation Network............. 2471
`Toshiaki Fukada, Yoshinori Sagisaka
`ATR ITL, Japan
`
`|
`
`Th4A.5 Whatis Wrong with the Lexicon-An Attemptto
`Model Pronunciations Probabilistically .........6ssuse 2475
`Uwe Jost, Henrik Heine, Gunnar Evermann
`Hamburg Univ., Germany
`
`Th4A.6 Lexical Tuning Based on Triphone Confidence
`Estimation .........cceccccssssscsessscssssessssnssseesssessseasssceesseaeees 2479
`Kevin L. Markey, *Wayne Ward
`Berdy Medical Systems, USA
`*Curnegie Mellon Univ., USA
`
`
`
`Th4B.1 Improving ofAmplitudeModulation Maps!forFO-
`Dependent Segregation of Harmonic Sounds...
`w= 2A83
`Frederic Berthommier, “Georg Meyer
`ICP, INPG, France
`*Univ. ofKeele, UK |
`Th4B.2 Psychophysical Evaluation of PSOLA: Natural
`Versus Synthetic Speechn........sccsssscsseesesesssessccesecseseenees2487
`Reinier Kortekaas, Armin Kohirausch
`IPO, The Netherlands
`
`Th4C.6 Designing a Speaker Adaptable Formant-Based
`Text-To-Speech System .....cccccsccseccssessersscenaeesBasecadeeceneaes 2527
`Vassilios Darsinos, Dimiftios Galanis, George Kokkinakis
`Univ. of Patras, Greece
`
`xliii
`
`
` r =
`
`Page 15 of 38
`
`Page 15 of 38
`
`

`

`Eurospeech:’97
`5"European Conference on Spéech Communication and Technology
`
`
`
`
`Th4D.1 On Using Fractal Features of Speech Sounds in
`Automatic Speech Recognition...........ccccsecsessneren 2531
`Petros Maragos;*Alexandros Potamianos
`.
`*
`ILSP & Georgia Tech, Greece & USA
`*AT&T Labs-Research, USA
`
`a
`
`¢
`
`v
`
`'
`
`Th4D.2 Dynamic Constraint Weighting in the Context of
`Articulatory Parameter Estimation :......0...0.cccccesssseneees 2535
`HywelB. Richards,John S. Bridle, Melvyn J. Hunt, “John S.
`Mason
`Dragon Systems, UK
`*Univ, of Wales Swansea, UK
`
`Th4D.3 Estimation of Vocal Tract Front Cavity Resonance
`in Unvoiced Fricative Speech ..0..........csccscsesssesssssssssseses 2539
`Minkyu Lee, Donald G. Childers
`Univ. of Florida, USA
`
`Th4D.4 A Software Tool to StudyPortuguese Vowels
`AntonioTeixeira, Francisco’‘Vaz, *Jose Carlos Principe
`INESC,Portugal
`*Univ. ofFlorida, USA uc scccssssscsssssssescsssessessssessssassesesens sane 2543
`
`‘
`Th4D.5 Post-Synchronization Via Formant-to-Area
`Mapping of Asynchronously Recorded Speech Signals and“
`Area Functions..........csccccsescesssessersesserenesbesesachesarnseessereeeZo47]
`Jean Schoentgen, Sorin Ciocea
`'
`.
`Univ. Libre de Bruxelles, Belgium
`
`.
`Th4D.6 Geometrically and Acoustically Optimized
`*
`Codebook for Unique Mapping from Formants to Vocal-
`Tract Shape...ee ecessescecscseecesesssssesessnssesesnessessenesense 2551
`Zhenli L. Yu, P.C. Ching
`The Chinese Univ. ofHong Kong, Hong Kong
`
`
`
`ThAA.1 Noisy Speech Enhancement by Fusion of Auditory
`and Visual Information: A Study of Vowel
`TYAMsitins .........ccccccscsssssessescecsesesscsestensesescstencasesssessuensocen 2555
`Laurent Girin, Gang Feng,Jean-LucSchwartz
`|.
`'
`tof 7
`Univ. ofStendhal, France
`.
`
`ThAA.2 Spectral Subtraction Using a Non-Critically
`Decimated Discrete Wavelet Transform ..............0.sss00 2559
`Andreas Engelberg, Thomas Gulzow, ,_
`Univ. ofKiel, Germany
`
`:
`TbhAA.3 Bayesian Affine TrasformationofHMM,
`Parameters for Instantaneous and Supervised Adaptation ,
`in Telephone Speech Recognition. ................000. qeenteseeeee 2563
`Jen-Tzung Chien, Hsiao-Chuan Wang, *Chin-Hui Lee
`National Tsing Hua Univ., ROChina
`*Bell Labs, USA
`
`ThAA.5 Acoustic Front‘Ends forSpeaker-Independent
`Digit Recognition in Car Environments .................000.....2571
`Detlev Langmann, AlexanderFischer, Friedhelm Wuppermann,
`Reinhold Haeb-Umbach, Thomas Eisele
`.
`Philips GmbH, Germany
`
`ThAA.6 Signal Bids Removal Using the Multi-Path
`Stochastic Equalization Technique..........0:sccscssssesseess2575
`Lionel Delphin-Poulat, Chafic Mokbel
`France Telecom, France
`
`ThAA.7 Subband Echo Cancellation in Automatic Speech
`Dialog Systerts ........cssssssssscesssacccssesssssesssassassessssseceseseecesees2579
`Andrej Miksic, Bogomir Horvat
`Univ. ofMaribor, Slovenia
`ThAA.8 SpeechEnhancencement Via Energy Separation
`Hesham Tolba, Douglas O'Shaughnessy
`Univ, du Quebec, Cumadis .rcccccccccccccssscsccesnssascssessssercessensesee2583 .
`ThAA.9A MethodofSignalExtractionfromNoisy Signal
`Masashi Unoki, Masato Akagi ....ccsccsssssesssssssssssscuessssteeee2587
`Japan Advanced Institute ofScience und Technology, Japun
`
`ThAA.10 Multi-Channel Noise Reduction Using Wavelet
`Filter Bank...sccceessssssssssssssssssacessssessasscsussssaseneeseees2591
`Jiri Sika, Vratislav Davidek
`.
`Czech Technical Univ., Czech Republic
`
`ThAA.11 Speech Signal Detection in Noisy Environment
`Using a Local Entropic Criterion......0.0:...cccssscscscesessesaes2595
`Imad Abdallah, Silvio Montresor, Marc Baudry ’
`Laboratoire d'Informatique de Univ. du Maine, France
`
`ThAA.12 A New Algorithm for Robust Speech Recognition:
`t
`+"4
`The DeltaVector Taylor Series Approach
`:
`Pedro J. Moreno, Brian Eberman
`Digital Equipment Corp., USA...c.ccccccsscsessssssssssssonsassesssess2599
`
`ThAA.13 Robust Enhancement of Reverberant Speech
`Using Iterative Noise Removal) .............0.cccssscsesesesLs2603
`David Cole, Miles Moody, Sridha Sridharan
`*
`.
`Queensland Univ. ofTechnology, Australia wae
`
`ThAA.14 A Network Speech Echo Canceller with Comfort
`NOISE .0.0.......scccsssecsoccsscessccnsacsensssesgrocsatstusesseesesasaacssscsencaseees2607
`David J. Jones, Scott D. Watson, Kenneth G. Evans, Barry
`~~
`M.G. Cheetham, *Robert A. Reeves
`Univ. ofLiverpool, UK
`*BT Laboratories, UK
`
`v4
`
`' ‘
`
`°
`
`i
`
`Jo
`
`ThAAIS A Metric for Selecting Sub-Band Processing in
`Adaptive Speech Enhancement Systems...........s:csssese2611
`Amir Hussain, Douglas R. Campbell, Thomas J. Moir
`Univ. ofPuisley, UK
`
`ThAA.16 Estimation of LPC Cepstrum Vector of Speech -
`Contaminated by Additive Noise and its Application to
`Speech Enhancement....00.0........ccccscssssssesssssevsssccseceeseseess2615
`Hidefumi Kobatake, Hideta Suzuki
`Tokyo Univ. ofAgriculture & Technology, Japan
`
`ThAA- Integrated Bias Removal Techniques for Robust
`Speech Recognition ............ccsssssssssesssessecsnsessesssscssesnenss 2567
`Craig Lawrence, Mazin Rahim
`Univ. ofMaryland, USA
`
`ThAA.17, Multi-Band and Adaptation Approachesto
`Robust Speech Recognition .............ssscssessessessssssesssesesees2619
`Sangita Tibrewala, Hynek Hermansky
`Oregon Gruduute Institute ofScience und Technology, USA
`
`xliv
`c—--._————n
`
`Page 16 of 38
`
`Page 16 of 38
`
`

`

`Eurospeech °97
`5" European Conference on Speech Communication‘and Technology
`
`
`ThAA.18 Non-Quadratic Criterion Algorithms